Wechat Search Release

PassAudited by ClawScan on May 10, 2026.

Overview

This appears to be a benign public WeChat article search helper, with some implementation and supply-chain hygiene notes users should notice.

This skill looks safe for public WeChat article searches. Avoid using confidential search terms, do not rely on the documented robots/rate-limit/User-Agent guarantees unless your OpenClaw web tooling enforces them, and use an isolated environment if you manually install the Python dependencies.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI07: Insecure Inter-Agent Communication

What this means

Private or sensitive search terms could be shared with the configured web-search/fetch provider.

Why it was flagged

The user's query is sent through OpenClaw's web_search tool. This is expected for a search skill, but it means search terms may leave the local environment through the configured web provider.

Skill content

subprocess.run([
                'openclaw', 'tool', 'web_search',
                '--query', search_query,
                '--count', str(max_results)
            ], capture_output=True, text=True, timeout=30)

Recommendation

Use this skill for public/non-sensitive searches unless you are comfortable with your OpenClaw web provider’s data handling.

Low

#ASI09: Human-Agent Trust Exploitation

What this means

Users may overestimate the skill’s compliance behavior if they rely only on the documentation claims.

Why it was flagged

These are strong compliance guarantees, but the provided Python tool calls do not clearly enforce or pass robots.txt, delay, or User-Agent controls. This is a trust/implementation note rather than evidence of malicious behavior.

Skill content

- **Respects robots.txt**: Checks and follows robots.txt directives
- **Rate limiting**: Minimum 5-second delay between requests
- **Transparent identification**: Clear User-Agent string identifying the bot

Recommendation

Treat the compliance claims as intentions unless verified in the OpenClaw web tools or updated code.

Info

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Manual installation could pull dependency versions that were not reviewed with this artifact set.

Why it was flagged

If users manually install these dependencies, the lower-bound version specifiers allow newer package versions; there is no lockfile or install spec in the provided artifacts.

Skill content

requests>=2.25.0
beautifulsoup4>=4.9.0
pytest>=6.0.0
pytest-cov>=2.10.0
mock>=4.0.0

Recommendation

Install in an isolated environment and pin or review dependency versions if you choose to run the Python helper.